How real projects brief Codex, Cursor and every other agent that reads AGENTS.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
VercelAGENTS.mdvercel/next.js/packages/next/AGENTS.md
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in dist/docs/ before writing any code. Heed deprecation notices.
No other project uses it yet
VercelAGENTS.mdvercel/next.js/test/AGENTS.md
All newly created e2e tests must work with Cache Components both enabled and disabled. The test infrastructure runs both variants. In the enabled variant, __NEXT_CACHE_COMPONENTS=true enables Cache Components even when the fixture's next.config does not declare cacheComponents. - Write fixtures that conform to Cache Components rules by default: put uncached or request-time work behind appropriate <Suspense> boundaries, and use "use cache" for work that should be cached. Preserve what the test is intended to cover when adapting the fixture. -…
Steady2 mentions in 2 weeks
No other project uses it yet
VercelAGENTS.mdvercel/next.js/turbopack/AGENTS.md
Turbopack is a general-purpose bundler that is built and designed for Next.js, but is not necessarily Next.js-specific. Keep Next.js concepts out of it. These rules apply throughout this directory tree when developing with turbo_tasks:
Steady2 mentions in 2 weeks
No other project uses it yet
MicrosoftAGENTS.mdmicrosoft/PowerToys/AGENTS.md
Top-level AI contributor guidance for developing PowerToys - a collection of Windows productivity utilities
No other project uses it yet
OpenAIAGENTS.mdopenai/codex/codex-rs/code-mode-host/AGENTS.md
Do not use timeouts or sleeps to synchronize tests. Wait for explicit signals or observable state; let the test runner enforce test-case timeouts.
Steady13 mentions in 2 weeks
No other project uses it yet
OpenAIAGENTS.mdopenai/codex/codex-rs/exec-server/src/sandbox_integrity/AGENTS.md
These checks currently emit telemetry only. Findings and preparation errors must not change sandbox construction, permissions, approvals, or command execution. Supported backends are Seatbelt, bubblewrap, and MXC; legacy Windows is out of scope. - Backends supply complete dependency inventories and interpret the request's original filesystem policy: resolve command temp directories and MXC volumes, and reuse the backend's deny-glob expansion where enforcement expands globs. - The runner prepares dependency facts and invokes each checker per dependency. Checkers remain independent of inventories…
Steady13 mentions in 2 weeks
No other project uses it yet
OpenAIAGENTS.mdopenai/codex/codex-rs/tui/src/bottom_pane/AGENTS.md
When changing the paste-burst or chat-composer state machines in this folder, keep the docs in sync: - Update the relevant module docs (chat_composer.rs and/or paste_burst.rs) so they remain a readable, top-down explanation of the current behavior. - Keep implementations/docstrings aligned unless a divergence is intentional and documented. Practical check: - After edits, sanity-check that docs mention only APIs/behavior that exist in code (especially the Enter/newline paths and disable_paste_burst semantics).
Steady13 mentions in 2 weeks
No other project uses it yet
SupabaseAGENTS.mdsupabase/supabase/AGENTS.md
pnpm 11 + Turborepo monorepo. Requires Node >= 22.13. Every PR must pass typecheck + lint (one workflow), Prettier, and a typos check. Other checks are path-filtered: Studio unit tests/build and the lint ratchet (ESLint warning count must not increase) run on apps/studio/** changes and the Tailwind class rules (shadcn/*) for www, docs, design-system, ui-library, and learn; app-specific test suites run on their own paths. Never hand-edit generated files: packages/api-types/types/**, **/routeTree.gen.ts, **/__generated__/**
No other project uses it yet
SupabaseAGENTS.mdsupabase/supabase/apps/docs/AGENTS.md
Next.js app router + MDX. Dev server: pnpm dev:docs → http://localhost:3001/docs (the bare / 404s). style-guide/ holds the docs style guide as plain markdown. Load the file you need rather than the whole directory. No tool enforces the guide, so applying it is the author's job, or the skill's. Load these before working. pm-the-docs, write-the-docs, edit-the-docs, ask-the-docs, and review-the-docs back the docs authoring process. See CONTRIBUTING.md for which stage each covers. They apply the style guide above. For architecture questions…
No other project uses it yet
SupabaseAGENTS.mdsupabase/supabase/apps/studio/AGENTS.md
Next.js pages router + TanStack Start (mid-migration, see below), React 19. Dev server: pnpm dev:studio → http://localhost:8082. Load the skills matching the task; stack them when a task spans areas: Studio is migrating from the Next.js pages router (pages/**) to TanStack Start (routes/**). Both runtimes ship side-by-side; the STUDIO_FRAMEWORK env var selects which one pnpm dev/build runs (default: next, resolved in scripts/dispatch.js). Full route map and strategy: TANSTACK_MIGRATION.md.
No other project uses it yet
MicrosoftAGENTS.mdmicrosoft/terminal/AGENTS.md
These rules apply to all public contributions and interactions, no matter how they're done. The entity operating or authorizing the contributions and interactions is responsible for them. AI assistance does not relieve contributors of responsibility for their work. "The AI did it" is not an excuse. Violations may result in contributions being closed without further comment. Cases of deception, evasion, or repeat violations may result in account bans. Allowed: - All AI usage that remains non-public (e.g. questions, reviews, local…
No other project uses it yet
MicrosoftAGENTS.mdmicrosoft/playwright/AGENTS.md
playwright-chromium, playwright-firefox, playwright-webkit — per-browser distributions. playwright-browser-chromium, playwright-browser-firefox, playwright-browser-webkit — binary packages. Assume watch is running and code is up to date. Generated files (types, channels, validators) are produced by watch automatically. Runs all lint checks in parallel: eslint, tsc, doclint, check-deps, generate_channels, generate_types, lint-tests, test-types, lint-packages, code-snippet linting, check-dependency-age (every version in package-lock.json must be at least 7 days old). Run flint only before you upload a PR, and only after npm run build. Do not run it before…
No other project uses it yet
Model Context ProtocolAGENTS.mdmodelcontextprotocol/servers/src/everything/AGENTS.md
The repo-wide TypeScript, naming and MCP rules are in the root AGENTS.md, which is loaded in every session. This file holds only what is specific to this server, and is…
Steady3 mentions in 2 weeks
No other project uses it yet
AstralAGENTS.mdastral-sh/uv/AGENTS.md
- Read CONTRIBUTING.md for guidelines on how to run tools - ALWAYS ensure that new tests use the same style as existing tests for all parts of the test - ALWAYS check whether the behavior of a new test is already covered by an existing test - DO NOT run integration test scenarios in loops or share their snapshots with insta::allow_duplicates!. Write explicit command invocations and snapshots; use separate named tests for independent scenarios - DO NOT repeat integration tests…
Steady3 mentions in 2 weeks
No other project uses it yet
ElasticAGENTS.mdelastic/elasticsearch/AGENTS.md
Stateless Elasticsearch is a distribution where shard data is stored in an object store (e.g., S3, GCS, Azure) rather than local disk. Nodes carry no durable local state. The cluster…
No other project uses it yet
ElasticAGENTS.mdelastic/elasticsearch/benchmarks/AGENTS.md
Run from the benchmarks/ directory using the run task with --args. Always use the fully-qualified class name including package to avoid ambiguity. Always pipe through tee /tmp/bench/<descriptive_name> using a filename…
No other project uses it yet
ElasticAGENTS.mdelastic/elasticsearch/docs/AGENTS.md
Always run docs-builder from the root of the checkout, not from a subdirectory. Running from a subdirectory will only validate that subdirectory's links and may silently miss errors in cross-document…
No other project uses it yet
OpenAIAGENTS.mdopenai/openai-cookbook/examples/agents_sdk/sandboxed-code-migration/migration_agent/AGENTS.md
You are migrating the mounted repo under repo/. - Migrate the repo according to repo/MIGRATION.md. - Preserve the public function signatures and behavior. - Run the baseline test command before editing. - Edit the app code and its tests. - Run the check command named in repo/MIGRATION.md after editing. - Run the final test command named in repo/MIGRATION.md after editing. - Return structured output that includes the exact commands, pass/fail summaries, changed files, a Markdown migration report, and the patch…
No other project uses it yet
ClineAGENTS.mdcline/cline/sdk/AGENTS.md
Development reference for the Cline SDK workspace.
No other project uses it yet
ClineAGENTS.mdcline/cline/sdk/packages/llms/AGENTS.md
Development guidance for the @cline/llms package.
No other project uses it yet
An open format for instructions to coding agents, read by Codex, Cursor and others. Think of it as a README written for agents.
At the repository root, with more specific files in subdirectories. Agents read the one closest to the file they're editing.
Setup and test commands, code style, and the rules a new contributor would need to know.
Claude Code reads CLAUDE.md. A one-line CLAUDE.md that points at AGENTS.md covers both.
